Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15575
    Prev
    Next
    INDEX
    Explanations

    food-related descriptors and terms associated with culinary experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Food, cuisine, and dishes

    np_acts-logits-general · gemini-2.0-flash

    food offerings and recommendations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pegat
    -0.57
     poussière
    -0.57
     coser
    -0.55
    asteroide
    -0.52
     vettoriale
    -0.52
    glMatrixMode
    -0.50
    amodel
    -0.50
     femei
    -0.50
    endela
    -0.49
     saveiro
    -0.49
    POSITIVE LOGITS
     delicious
    1.42
     tasty
    1.17
     culinary
    1.13
     yummy
    1.11
     flavors
    1.08
     delicacies
    1.08
     taste
    1.06
     gourmet
    1.05
    delicious
    1.05
     tastes
    1.04
    Activations Density 0.340%

    No Known Activations